AAAI 2022 论文列表

For users to trust planning algorithms, they must be able to understand the planner's outputs and the reasons for each action selection. This output does not tend to be user-friendly, often consisting of sequences of parametrised actions or task networks. And these may not be practical for non-expert users who may find it easier to read natural language descriptions. In this paper, we propose PlanVerb, a domain and planner-independent method for the verbalization of task plans. It is based on semantic tagging of actions and predicates. Our method can generate natural language descriptions of plans including causal explanations. The verbalized plans can be summarized by compressing the actions that act on the same parameters. We further extend the concept of verbalization space, previously applied to robot navigation, and apply it to planning to generate different kinds of plan descriptions for different user requirements. Our method can deal with PDDL and RDDL domains, provided that they are tagged accordingly. Our user survey evaluation shows that users can read our automatically generated plan descriptions and that the explanations help them answer questions about the plan.

We study the computational complexity of computing solutions for the straight-cut and square-cut pizza sharing problems. We show that finding an approximate solution is PPA-hard for the straight-cut problem, and PPA-complete for the square-cut problem, while finding an exact solution for the square-cut problem is FIXP-hard and in BU. Our PPA-hardness results apply even when all mass distributions are unions of non-overlapping squares, and our FIXP-hardness result applies even when all mass distributions are unions of weighted squares and right-angled triangles. We also prove that decision variants of the square-cut problem are hard: the approximate problem is NP-complete, and the exact problem is ETR-complete.

Recent studies in the hate and counter hate domain have provided the grounds for investigating how to detect this pervasive content in social media. These studies mostly work with synthetic replies to hateful content written by annotators on demand rather than replies written by real users. We argue that working with naturally occurring replies to hateful content is key to study the problem. Building on this motivation, we create a corpus of 5,652 hateful tweets and replies. We analyze their fine-grained relationships by indicating whether the reply (a) is hate or counter hate speech, (b) provides a justification, (c) attacks the author of the tweet, and (d) adds additional hate. We also present linguistic insights into the language people use depending on these fine-grained relationships. Experimental results show improvements (a) taking into account the hateful tweet in addition to the reply and (b) pretraining with related tasks.

Single image generation (SIG), described as generating diverse samples that have the same visual content as the given natural image, is first introduced by SinGAN, which builds a pyramid of GANs to progressively learn the internal patch distribution of the single image. It shows excellent performance in a wide range of image manipulation tasks. However, SinGAN has some limitations. Firstly, due to lack of semantic information, SinGAN cannot handle the object images well as it does on the scene and texture images. Secondly, the independent progressive training scheme is time-consuming and easy to cause artifacts accumulation. To tackle these problems, in this paper, we dig into the single image generation problem and improve SinGAN by fully-utilization of internal and external priors. The main contributions of this paper include: 1) We interpret single image generation from the perspective of the general generative task, that is, to learn a diverse distribution from the Dirac distribution composed of a single image. In order to solve this non-trivial problem, we construct a regularized latent variable model to formulate SIG. To the best of our knowledge, it is the first time to give a clear formulation and optimization goal of SIG, and all the existing methods for SIG can be regarded as special cases of this model. 2) We design a novel Prior-based end-to-end training GAN (PetsGAN), which is infused with internal prior and external prior to overcome the problems of SinGAN. For one thing, we employ the pre-trained GAN model to inject external prior for image generation, which can alleviate the problem of lack of semantic information and generate natural, reasonable and diverse samples, even for the object image. For another, we fully-utilize the internal prior by a differential Patch Matching module and an effective reconstruction network to generate consistent and realistic texture. 3) We construct abundant of qualitative and quantitative experiments on three datasets. The experimental results show our method surpasses other methods on both generated image quality, diversity, and training speed. Moreover, we apply our method to other image manipulation tasks (e.g., style transfer, harmonization) and the results further prove the effectiveness and efficiency of our method.

Omnidirectional images, also called 360◦images, have attracted extensive attention in recent years, due to the rapid development of virtual reality (VR) technologies. During omnidirectional image processing including capture, transmission, consumption, and so on, measuring the perceptual quality of omnidirectional images is highly desired, since it plays a great role in guaranteeing the immersive quality of experience (IQoE). In this paper, we conduct a comprehensive study on the perceptual quality of omnidirectional images from both subjective and objective perspectives. Specifically, we construct the largest so far subjective omnidirectional image quality database, where we consider several key influential elements, i.e., realistic non-uniform distortion, viewing condition, and viewing behavior, from the user view. In addition to subjective quality scores, we also record head and eye movement data. Besides, we make the first attempt by using the proposed database to train a convolutional neural network (CNN) for blind omnidirectional image quality assessment. To be consistent with the human viewing behavior in the VR device, we extract viewports from each omnidirectional image and incorporate the user viewing conditions naturally in the proposed model. The proposed model is composed of two parts, including a multi-scale CNN-based feature extraction module and a perceptual quality prediction module. The feature extraction module is used to incorporate the multi-scale features, and the perceptual quality prediction module is designed to regress them to perceived quality scores. The experimental results on our database verify that the proposed model achieves the competing performance compared with the state-of-the-art methods.

We introduce Perceiving Stroke-Semantic Context (PerSec), a new approach to self-supervised representation learning tailored for Scene Text Recognition (STR) task. Considering scene text images carry both visual and semantic properties, we equip our PerSec with dual context perceivers which can contrast and learn latent representations from low-level stroke and high-level semantic contextual spaces simultaneously via hierarchical contrastive learning on unlabeled text image data. Experiments in un- and semi-supervised learning settings on STR benchmarks demonstrate our proposed framework can yield a more robust representation for both CTC-based and attention-based decoders than other contrastive learning methods. To fully investigate the potential of our method, we also collect a dataset of 100 million unlabeled text images, named UTI-100M, covering 5 scenes and 4 languages. By leveraging hundred-million-level unlabeled data, our PerSec shows significant performance improvement when fine-tuning the learned representation on the labeled data. Furthermore, we observe that the representation learned by PerSec presents great generalization, especially under few labeled data scenes.

We present a general framework for training safe agents whose naive incentives are unsafe. As an example, manipulative or deceptive behaviour can improve rewards but should be avoided. Most approaches fail here: agents maximize expected return by any means necessary. We formally describe settings with `delicate' parts of the state which should not be used as a means to an end. We then train agents to maximize the causal effect of actions on the expected return which is not mediated by the delicate parts of state, using Causal Influence Diagram analysis. The resulting agents have no incentive to control the delicate state. We further show how our framework unifies and generalizes existing proposals.

Large capacity deep learning models are often prone to a high generalization gap when trained with a limited amount of labeled training data. A recent class of methods to address this problem uses various ways to construct a new training sample by mixing a pair (or more) of training samples. We propose PatchUp, a hidden state block-level regularization technique for Convolutional Neural Networks (CNNs), that is applied on selected contiguous blocks of feature maps from a random pair of samples. Our approach improves the robustness of CNN models against the manifold intrusion problem that may occur in other state-of-the-art mixing approaches. Moreover, since we are mixing the contiguous block of features in the hidden space, which has more dimensions than the input space, we obtain more diverse samples for training towards different dimensions. Our experiments on CIFAR10/100, SVHN, Tiny-ImageNet, and ImageNet using ResNet architectures including PreActResnet18/34, WRN-28-10, ResNet101/152 models show that PatchUp improves upon, or equals, the performance of current state-of-the-art regularizers for CNNs. We also show that PatchUp can provide a better generalization to deformed samples and is more robust against adversarial attacks.

Detection of manipulated face images has attracted a lot of interest recently. Various schemes have been proposed to tackle this challenging problem, where the patch-based approaches are shown to be promising. However, the existing patch-based approaches tend to treat different patches equally, which do not fully exploit the patch discrepancy for effective feature learning. In this paper, we propose a Patch Diffusion (PD) module which can be integrated into the existing face manipulation detection networks to boost the performance. The PD consists of Discrepancy Patch Feature Learning (DPFL) and Attention-Aware Message Passing (AMP). The DPFL effectively learns the patch features by a newly designed Pairwise Patch Loss (PPLoss), which takes both the patch importance and correlations into consideration. The AMP diffuses the patches through attention-aware message passing in a graph network, where the attentions are explicitly computed based on the patch features learnt in DPFL. We integrate our PD module into four recent face manipulation detection networks, and carry out the experiments on four popular datasets. The results demonstrate that our PD module is able to boost the performance of the existing networks for face manipulation detection.

When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would like our AI agents to effectively collaborate in a similar way by capturing a model of their partners. In this work, we propose and analyze a decentralized Multi-Armed Bandit (MAB) problem with coupled rewards as an abstraction of more general multi-agent collaboration. We demonstrate that naive extensions of single-agent optimal MAB algorithms fail when applied for decentralized bandit teams. Instead, we propose a Partner-Aware strategy for joint sequential decision-making that extends the well-known single-agent Upper Confidence Bound algorithm. We analytically show that our proposed strategy achieves logarithmic regret, and provide extensive experiments involving human-AI and human-robot collaboration to validate our theoretical findings. Our results show that the proposed partner-aware strategy outperforms other known methods, and our human subject studies suggest humans prefer to collaborate with AI agents implementing our partner-aware strategy.

Participatory budgeting (PB) is a democratic process where citizens jointly decide on how to allocate public funds to indivisible projects. In this work, we focus on PB processes where citizens may provide additional money to projects they want to see funded. We introduce a formal framework for this kind of PB with donations. Our framework also allows for diversity constraints, meaning that each project belongs to one or more types, and there are lower and upper bounds on the number of projects of the same type that can be funded. We propose three general classes of methods for aggregating the citizens’ preferences in the presence of donations and analyze their axiomatic properties. Furthermore, we investigate the computational complexity of determining the outcome of a PB process with donations and of finding a citizen’s optimal donation strategy.

We consider a general task called partial Wasserstein covering with the goal of providing information on what patterns are not being taken into account in a dataset (e.g., dataset used during development) compared to another (e.g., dataset obtained from actual applications). We model this task as a discrete optimization problem with partial Wasserstein divergence as an objective function. Although this problem is NP-hard, we prove that it satisfies the submodular property, allowing us to use a greedy algorithm with a 0.63 approximation. However, the greedy algorithm is still inefficient because it requires solving linear programming for each objective function evaluation. To overcome this inefficiency, we propose quasi-greedy algorithms, which consist of a series of techniques for acceleration such as sensitivity analysis based on strong duality and the so-called C-transform in the optimal transport field. Experimentally, we demonstrate that we can efficiently fill in the gaps between the two datasets, and find missing scene in real driving scene datasets.

To deal with ambiguities in partial multi-label learning (PML), existing popular PML research attempts to perform disambiguation by direct ground-truth label identification. However, these approaches can be easily misled by noisy false-positive labels in the iteration of updating the model parameter and the latent ground-truth label variables. When labeling information is ambiguous, we should depend more on underlying structure of data, such as label and feature correlations, to perform disambiguation for partially labeled data. Moreover, large margin nearest neighbour (LMNN) is a popular strategy that considers data structure in classification. However, due to the ambiguity of labeling information in PML, traditional LMNN cannot be used to solve the PML problem directly. In addition, embedding is an effective technology to decrease the noise information of data. Inspried by LMNN and embedding technology, we propose a novel PML paradigm called Partial Multi-label Learning via Large Margin Nearest Neighbour Embeddings (PML-LMNNE), which aims to conduct disambiguation by projecting labels and features into a lower-dimension embedding space and reorganize the underlying structure by LMNN in the embedding space simultaneously. An efficient algorithm is designed to implement the proposed method and the convergence rate of the algorithm is analyzed. Moreover, we present a theoretical analysis of the generalization error bound for the proposed PML-LMNNE, which shows that the generalization error converges to the sum of two times the Bayes error over the labels when the number of instances goes to infinity. Comprehensive experiments on artificial and real-world datasets demonstrate the superiorities of the proposed PML-LMNNE.

k-center is one of the most popular clustering models. While it admits a simple 2-approximation in polynomial time in general metrics, the Euclidean version is NP-hard to approximate within a factor of 1.93, even in the plane, if one insists the dependence on k in the running time be polynomial. Without this restriction, a classic algorithm yields a 2^{O((klog k)/{epsilon})}dn-time (1+epsilon)-approximation for Euclidean k-center, where d is the dimension. In this work, we give a faster algorithm for small dimensions: roughly speaking an O^*(2^{O((1/epsilon)^{O(d)} k^{1-1/d} log k)})-time (1+epsilon)-approximation. In particular, the running time is roughly O^*(2^{O((1/epsilon)^{O(1)}sqrt{k}log k)}) in the plane. We complement our algorithmic result with a matching hardness lower bound. We also consider a well-studied generalization of k-center, called Non-uniform k-center (NUkC), where we allow different radii clusters. NUkC is NP-hard to approximate within any factor, even in the Euclidean case. We design a 2^{O(klog k)}n^2 time 3-approximation for NUkC, and a 2^{O((klog k)/epsilon)}dn time (1+epsilon)-approximation for Euclidean NUkC. The latter time bound matches the bound for k-center.

Multilingual neural machine translation (MNMT) aims to translate multiple languages with a single model and has been proved successful thanks to effective knowledge transfer among different languages with shared parameters. However, it is still an open question which parameters should be shared and which ones need to be task-specific. Currently, the common practice is to heuristically design or search language-specific modules, which is difficult to find the optimal configuration. In this paper, we propose a novel parameter differentiation based method that allows the model to determine which parameters should be language-specific during training. Inspired by cellular differentiation, each shared parameter in our method can dynamically differentiate into more specialized types. We further define the differentiation criterion as inter-task gradient similarity. Therefore, parameters with conflicting inter-task gradients are more likely to be language-specific. Extensive experiments on multilingual datasets have demonstrated that our method significantly outperforms various strong baselines with different parameter sharing configurations. Further analysis reveals that the parameter sharing configuration obtained by our method correlates well with the linguistic proximities.

As a key component of talking face generation, lip movements generation determines the naturalness and coherence of the generated talking face video. Prior literature mainly focuses on speech-to-lip generation while there is a paucity in text-to-lip (T2L) generation. T2L is a challenging task and existing end-to-end works depend on the attention mechanism and autoregressive (AR) decoding manner. However, the AR decoding manner generates current lip frame conditioned on frames generated previously, which inherently hinders the inference speed, and also has a detrimental effect on the quality of generated lip frames due to error propagation. This encourages the research of parallel T2L generation. In this work, we propose a parallel decoding model for fast and high-fidelity text-to-lip generation (ParaLip). Specifically, we predict the duration of the encoded linguistic features and model the target lip frames conditioned on the encoded linguistic features with their duration in a non-autoregressive manner. Furthermore, we incorporate the structural similarity index loss and adversarial learning to improve perceptual quality of generated lip frames and alleviate the blurry prediction problem. Extensive experiments conducted on GRID and TCD-TIMIT datasets demonstrate the superiority of proposed methods.

Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (i.e., StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. Besides, there is still a noticeable visual quality gap compared with pre-trained GAN models. In this paper, we propose a novel GAN Prior based degradation-aware feature interpolation network, dubbed Panini-Net, for FR tasks by explicitly learning the abstract representations to distinguish various degradations. Specifically, an unsupervised degradation representation learning (UDRL) strategy is first developed to extract degradation representations (DR) of the input degraded images. Then, a degradation-aware feature interpolation (DAFI) module is proposed to dynamically fuse the two types of informative features (i.e., features from input images and features from GAN Prior) with flexible adaption to various degradations based on DR. Ablation studies reveal the working mechanism of DAFI and its potential for editable FR. Extensive experiments demonstrate that our Panini-Net achieves state-of-the-art performance for multi-degradation face restoration and face super-resolution. The source code is available at https://github.com/jianzhangcs/panini.

In remote sensing imaging systems, pan-sharpening is an important technique to obtain high-resolution multispectral images from a high-resolution panchromatic image and its corresponding low-resolution multispectral image. Owing to the powerful learning capability of convolution neural network (CNN), CNN-based methods have dominated this field. However, due to the limitation of the convolution operator, long-range spatial features are often not accurately obtained, thus limiting the overall performance. To this end, we propose a novel and effective method by exploiting a customized transformer architecture and information-lossless invertible neural module for long-range dependencies modeling and effective feature fusion in this paper. Specifically, the customized transformer formulates the PAN and MS features as queries and keys to encourage joint feature learning across two modalities while the designed invertible neural module enables effective feature fusion to generate the expected pan-sharpened results. To the best of our knowledge, this is the first attempt to introduce transformer and invertible neural network into pan-sharpening field. Extensive experiments over different kinds of satellite datasets demonstrate that our method outperforms state-of-the-art algorithms both visually and quantitatively with fewer parameters and flops. Further, the ablation experiments also prove the effectiveness of the proposed customized long-range transformer and effective invertible neural feature fusion module for pan-sharpening.

Recently, Transformers have shown promising performance in various vision tasks. To reduce the quadratic computation complexity caused by the global self-attention, various methods constrain the range of attention within a local region to improve its efficiency. Consequently, their receptive fields in a single attention layer are not large enough, resulting in insufficient context modeling. To address this issue, we propose a Pale-Shaped self-Attention (PS-Attention), which performs self-attention within a pale-shaped region. Compared to the global self-attention, PS-Attention can reduce the computation and memory costs significantly. Meanwhile, it can capture richer contextual information under the similar computation complexity with previous local self-attention mechanisms. Based on the PS-Attention, we develop a general Vision Transformer backbone with a hierarchical architecture, named Pale Transformer, which achieves 83.4%, 84.3%, and 84.9% Top-1 accuracy with the model size of 22M, 48M, and 85M respectively for 224x224 ImageNet-1K classification, outperforming the previous Vision Transformer backbones. For downstream tasks, our Pale Transformer backbone performs better than the recent state-of-the-art CSWin Transformer by a large margin on ADE20K semantic segmentation and COCO object detection & instance segmentation. The code will be released on https://github.com/BR-IDL/PaddleViT.